Ecological environment monitoring system and method

Abstract

The invention provides an ecological environment monitoring system and method, and the method comprises the steps: building a three-dimensional digital twinborn model of a designated city in a target region, and enabling the three-dimensional digital twinborn model to comprise thermal environment dynamic data of different environment nodes; determining spatial structure characteristics of different environment nodes, and constructing a spatial communication relationship through the spatial structure characteristics; determining diffusion intensity indexes of each environment node in different thermal diffusion ranges, and further determining the heat island effect intensity of each environment node by combining all the diffusion intensity indexes with the spatial communication relationship; based on the heat island effect intensity, evaluating the influence of the heat island effect intensity on a pollution diffusion field, and obtaining the heat influence pollution diffusion risk of each environment node in different heat diffusion ranges; and generating a multi-scale thermal pollution report of the target area through all the thermal influence pollution diffusion risks. By adopting the scheme of the invention, multi-scale monitoring can be carried out on urban thermal pollution based on a space-time cooperation mechanism of digital twinning.

Description

Technical Field

[0001] This application relates to the field of environmental monitoring technology, and more specifically, to an ecological environment monitoring system and method. Background Technology

[0002] Environmental monitoring involves real-time, continuous, and systematic observation and analysis of various elements in the natural environment. It aims to understand the environmental quality status, assess the degree of environmental pollution, and provide a scientific basis for environmental management and decision-making. This field covers multiple monitoring objects and can combine advanced technologies such as multi-source sensors, remote sensing imaging, wireless communication, edge computing, and artificial intelligence to achieve high-precision perception and analysis of key parameters such as atmospheric particulate matter, ozone, volatile organic compounds, heavy metal ions, and biodiversity indicators.

[0003] Ecological and environmental monitoring refers to the continuous, dynamic, and comprehensive observation and assessment of various environmental elements in natural ecosystems. Its core objective is to comprehensively understand the status of ecological and environmental quality, identify potential risks, and provide scientific support for ecological protection and environmental management. In actual monitoring, thermal pollution, as a non-traditional type of pollution, is receiving increasing attention. It mainly refers to the abnormal heat release caused by industrial emissions, urban heat island effect, or infrastructure operation, leading to an abnormal rise in environmental temperature and thus affecting the ecological balance. In the existing urban thermal pollution monitoring process, there is a lack of systematic simulation of the thermal pollution and pollutant diffusion process in the three-dimensional spatial structure of the city, which makes it impossible for environmental monitoring systems to quantify the impact of the urban heat island effect on pollution diffusion. Therefore, how to conduct multi-scale monitoring of urban thermal pollution based on the spatiotemporal collaborative mechanism of digital twins has become a challenge for the industry. Summary of the Invention

[0004] This application provides an ecological environment monitoring system and method that can monitor urban thermal pollution at multiple scales based on a spatiotemporal collaborative mechanism of digital twins.

[0005] Firstly, this application provides an ecological environment monitoring method, comprising the following steps: Construct a three-dimensional digital twin model of a specified city in a target area, wherein the three-dimensional digital twin model includes dynamic thermal environment data of different environmental nodes; The spatial structural features of different environmental nodes in the three-dimensional digital twin model are determined, and then the spatial connectivity between all adjacent environmental nodes in the three-dimensional digital twin model is constructed through the spatial structural features. The diffusion intensity index of each environmental node under different thermal diffusion ranges is determined by the dynamic data of the thermal environment. Then, all diffusion intensity indices are combined with the spatial connectivity relationship to perform spatiotemporal convolution aggregation on the target area to obtain the heat island effect intensity of each environmental node under different thermal diffusion ranges. Based on pollution monitoring data of different environmental nodes, a pollution diffusion field of each environmental node in a preset spatial neighborhood is generated. Then, based on the intensity of the heat island effect, its impact on the pollution diffusion field is assessed, and the thermal impact pollution diffusion risk of each environmental node in different heat diffusion ranges is obtained. A multi-scale thermal pollution report for the target area is generated by combining all thermal impact pollution spread risks with preset monitoring thresholds.

[0006] In some embodiments, determining the spatial structural features of different environmental nodes in the three-dimensional digital twin model specifically includes: Obtain the spatial parameters of each environmental node in the three-dimensional digital twin model; The spatial structural features of different environmental nodes in the three-dimensional digital twin model are determined by the spatial parameters.

[0007] In some embodiments, constructing the spatial connectivity relationships between all adjacent environmental nodes of the three-dimensional digital twin model through the spatial structural features specifically includes: Obtain the three-dimensional coordinates of each environmental node in the three-dimensional digital twin model; The diffusion attenuation factor between different adjacent environmental nodes is determined using all three-dimensional coordinates. Based on all diffusion attenuation factors and the spatial structural features, the spatial connectivity relationships between all adjacent environmental nodes in the three-dimensional digital twin model are constructed.

[0008] In some embodiments, determining the diffusion intensity index of each environmental node under different thermal diffusion ranges using the dynamic thermal environment data specifically includes: Differential analysis was performed on the dynamic thermal environment data to obtain the thermal pulse information of each environmental node; The diffusion intensity index of each environmental node under different thermal diffusion ranges is determined by all thermal pulse information.

[0009] In some embodiments, combining all diffusion intensity indices with the spatial connectivity relationship to perform spatiotemporal convolution aggregation on the target region to obtain the heat island effect intensity of each environmental node in different thermal diffusion ranges specifically includes: A spatiotemporal thermal diffusion map model of the target region is constructed by combining all diffusion intensity indices and the aforementioned spatial connectivity relationships with a graph convolutional network algorithm. Based on the spatiotemporal heat diffusion map model, each environmental node is convolved and aggregated to obtain the intensity of the heat island effect of each environmental node in different heat diffusion ranges.

[0010] In some embodiments, generating a pollution diffusion field for each environmental node in a preset spatial neighborhood based on pollution monitoring data from different environmental nodes specifically includes: Obtain pollution monitoring data for each environmental node in the three-dimensional digital twin model; Select an environment node as the selected environment node; The amount of pollution drift of the selected environmental node in the preset spatial neighborhood is determined by using pollution monitoring data of the selected environmental node. Construct a pollution diffusion field for the selected environmental node in a preset spatial neighborhood based on all pollution drift amounts; Continue to determine the pollution diffusion field of the remaining environmental nodes in the preset spatial neighborhood.

[0011] In some embodiments, assessing the impact of the heat island effect intensity on the pollution diffusion field to obtain the thermal impact pollution diffusion risk of each environmental node in different thermal diffusion ranges specifically includes: Evaluate the multiple diffusion influence components between the intensity of the heat island effect and the corresponding pollution diffusion field in different thermal diffusion ranges of selected environmental nodes; Determine the thermal impact pollution diffusion risk of selected environmental nodes within different thermal diffusion ranges based on all diffusion impact components; Continue to determine the risk of thermal impact pollution diffusion at remaining environmental nodes within different thermal diffusion ranges.

[0012] In some embodiments, generating a multi-scale thermal pollution report for a target area by combining all thermal impact pollution diffusion risks with preset monitoring thresholds specifically includes: Set monitoring thresholds for different thermal diffusion ranges; The thermal pollution risk level of each environmental node in different thermal diffusion ranges was determined by all monitoring thresholds and all thermal impact pollution diffusion risks. A multi-scale thermal pollution report for the target area is generated based on all thermal pollution risk levels.

[0013] In some embodiments, the environmental node refers to a spatial unit within a target area that is divided according to a preset spatial gridding rule.

[0014] Secondly, this application provides an ecological environment monitoring system, comprising: A construction module is used to construct a three-dimensional digital twin model of a specified city in a target area, wherein the three-dimensional digital twin model includes dynamic thermal environment data of different environmental nodes; The processing module is used to determine the spatial structural features of different environmental nodes in the three-dimensional digital twin model, and then construct the spatial connectivity relationship between all adjacent environmental nodes of the three-dimensional digital twin model through the spatial structural features. The processing module is also used to determine the diffusion intensity index of each environmental node under different thermal diffusion ranges through the thermal environment dynamic data, and then combine all diffusion intensity indices with the spatial connectivity relationship to perform spatiotemporal convolution aggregation on the target area to obtain the heat island effect intensity of each environmental node under different thermal diffusion ranges. The processing module is also used to generate pollution diffusion fields of each environmental node in a preset spatial neighborhood based on pollution monitoring data of different environmental nodes, and then assess its impact on the pollution diffusion field based on the intensity of the heat island effect to obtain the thermal impact pollution diffusion risk of each environmental node in different heat diffusion ranges. The execution module is used to generate a multi-scale thermal pollution report for the target area by combining all thermal impact pollution spread risks with preset monitoring thresholds.

[0015] The technical solutions provided by the embodiments disclosed in this application have the following beneficial effects: The ecological environment monitoring system and method provided in this application constructs a three-dimensional digital twin model of a designated city in a target area, wherein the three-dimensional digital twin model includes dynamic thermal environment data of different environmental nodes; determines the spatial structural characteristics of different environmental nodes in the three-dimensional digital twin model, and then constructs the spatial connectivity relationship between all adjacent environmental nodes in the three-dimensional digital twin model through the spatial structural characteristics; determines the diffusion intensity index of each environmental node under different thermal diffusion ranges through the dynamic thermal environment data, and then performs spatiotemporal convolution aggregation on the target area by combining all diffusion intensity indices with the spatial connectivity relationship to obtain the heat island effect intensity of each environmental node in different thermal diffusion ranges; generates a pollution diffusion field of each environmental node in a preset spatial neighborhood based on the pollution monitoring data of different environmental nodes, and then assesses its impact on the pollution diffusion field based on the heat island effect intensity to obtain the thermal impact pollution diffusion risk of each environmental node in different thermal diffusion ranges; and generates a multi-scale thermal pollution report of the target area by combining all thermal impact pollution diffusion risks with preset monitoring thresholds.

[0016] Therefore, in this application, firstly, after constructing a three-dimensional digital twin model of the designated city in the target area, the temperature changes and spatial adjacency relationships (spatial connectivity) of each environmental node within different heat diffusion ranges are integrated. The heat island effect intensity of each node is calculated at micro (e.g., street level), meso (e.g., district level), and even macro (e.g., city-wide level) scales. This maps the dispersed time-series surface temperature data onto the node grid in the three-dimensional digital twin model, allowing the temperature increment of the same node under different heat diffusion radii to be quantified as a comparable indicator. Secondly, by utilizing the spatial connectivity between nodes, the heat transmission paths in complex urban three-dimensional structures such as buildings, roads, and green spaces are effectively captured, thereby revealing the spatial distribution pattern of the heat island effect at different scales. Thus, the heat island effect intensity serves as a thermal sensitivity indicator within a multi-scale monitoring framework. Regional identification and temporal trend analysis lay a reliable data foundation, enabling environmental managers to intuitively understand the hierarchical distribution of thermal pollution based on real-time simulation results from digital twins, providing quantitative support for refined regulation and zoned governance. Subsequently, the impact of the heat island effect on the pollution diffusion field is assessed based on its intensity, yielding the thermal impact pollution diffusion risk of each environmental node within different thermal diffusion ranges. This thermal impact pollution diffusion risk guides the adaptive refinement of the dynamic grid in the digital twin, enabling the multi-scale monitoring system to output higher-precision risk warnings in hotspot areas through gridding. Simultaneously, by comparing with preset thresholds, tiered alarms and visual reports are automatically triggered, providing an end-to-end technical closed loop for coordinated urban heat-pollution governance. In summary, this solution can conduct multi-scale monitoring of urban thermal pollution based on the spatiotemporal coordination mechanism of digital twins. Attached Figure Description

[0017] Figure 1 This is a schematic flowchart of an ecological environment monitoring method according to some embodiments of this application; Figure 2 This is a flowchart illustrating the process of determining spatial connectivity according to some embodiments of this application; Figure 3 This is a schematic diagram of a structure for determining the level of thermal pollution risk according to some embodiments of this application; Figure 4 This is a schematic diagram of the structure of an ecological environment monitoring system according to some embodiments of this application; Figure 5 This is an internal structural diagram of a computer device for implementing an ecological environment monitoring method according to some embodiments of this application. Detailed Implementation

[0018] To better understand the technical solutions in this embodiment, the technical solutions in this embodiment will be described in detail below with reference to the accompanying drawings and specific implementation methods.

[0019] refer to Figure 1 The figure is a schematic flowchart of an ecological environment monitoring method according to some embodiments of this application. The ecological environment monitoring method mainly includes the following steps: In step 101, a three-dimensional digital twin model of the specified city in the target area is constructed, wherein the three-dimensional digital twin model includes dynamic thermal environment data of different environmental nodes.

[0020] In specific implementation, for a target area of ​​a designated city, basic three-dimensional spatial data describing the spatial range of the area can be obtained. This three-dimensional spatial data includes topographic elevation data, building outline data, road and water body distribution data, and green space distribution data of the target area, used to construct a three-dimensional geometric model of the target area. Subsequently, the target area is divided into multiple three-dimensional grid units according to preset spatial gridding rules, and each three-dimensional grid unit is treated as an environmental node. Each environmental node has a unique spatial location identifier in the three-dimensional coordinate system. The spatial gridding rules specify that the horizontal grid spacing of the three-dimensional grid unit can be 50 meters, and the vertical grid spacing can be 10 meters. Further, within the target area, various methods can be used, such as deploying ground environmental monitoring stations, deploying high-altitude sensors, and acquiring thermal infrared images from remote sensing satellites or UAVs, to obtain dynamic thermal environment data covering different time periods at the spatial locations corresponding to each environmental node. Then, through spatial interpolation algorithms, the aforementioned dynamic thermal environment data is mapped or interpolated from the actual sampling location to each environmental node, ensuring that each environmental node possesses dynamic thermal environment data that changes over time, thereby completing the construction of the three-dimensional digital twin model.

[0021] It should be noted that the three-dimensional digital twin model refers to a three-dimensional digital model constructed in virtual space that corresponds to the spatial structure and environmental information of the target area; the environmental node refers to a spatial unit divided within the target area according to a preset spatial gridding rule; and the dynamic thermal environment data refers to a collection of raw measurement data obtained through various environmental monitoring devices within a preset sampling period that reflects the thermal environment status of the target area.

[0022] In step 102, the spatial structural features of different environmental nodes in the three-dimensional digital twin model are determined, and then the spatial connectivity between all adjacent environmental nodes in the three-dimensional digital twin model is constructed through the spatial structural features.

[0023] In some embodiments, determining the spatial structural features of different environmental nodes in the three-dimensional digital twin model can be achieved using the following steps: Obtain the spatial parameters of each environmental node in the three-dimensional digital twin model; The spatial structural features of different environmental nodes in the three-dimensional digital twin model are determined by the spatial parameters.

[0024] It should be noted that the spatial parameters mentioned in this application refer to a set of data used to describe the basic physical attributes of each environmental node in the three-dimensional digital twin model, such as its position, shape, and scale in three-dimensional space. The spatial parameters include, but are not limited to, the spatial position coordinates of the environmental node in the three-dimensional coordinate system, the building height, building area, land area, roof area of ​​the building or land feature corresponding to the node, and the surface type information of the node's location. The extraction frequency of the spatial parameters can be set according to the accuracy of the monitoring task and the rate of change of the target area environment. For example, the spatial data of the three-dimensional digital twin model can be updated every 5 to 30 minutes to update the spatial parameters of the environmental nodes. In other embodiments, the spatial position and surrounding physical attributes (spatial parameters) of the environmental nodes can also be extracted by using spatial indexing or three-dimensional spatial topology analysis algorithms. This application does not limit this.

[0025] In specific implementation, determining the spatial structural features of different environmental nodes in the three-dimensional digital twin model through the spatial parameters can be achieved in the following way: First, for each environmental node, extract the corresponding spatial parameter data, including building area, building height, land area, green area, building volume, distance between nodes, and relative orientation information of adjacent buildings; then, according to the preset spatial structural feature calculation rules, calculate the spatial structural features of different environmental nodes respectively. Preferably, this specifically includes: using the ratio of building volume to land area as the building volume ratio of the environmental node, using the height difference between adjacent buildings of the environmental node as the spatial occlusion degree of the environmental node, and then using the building volume ratio and the spatial occlusion degree as the spatial structural features of the corresponding environmental node. In other embodiments, the ratio of green area to land area of ​​the node can also be used as the greening rate of the environmental node, etc., which is not limited here.

[0026] It should be noted that the spatial structural features mentioned in this application refer to a set of parameters used to characterize the spatial form and surrounding environment relationship of each environmental node in the three-dimensional digital twin model. Preferably, the spatial structural features include building volume ratio and spatial occlusion degree; wherein, the building volume ratio can be defined as the ratio of the building volume corresponding to the environmental node to the land area, which is used to reflect the building density; the spatial occlusion degree can be defined as the height difference between the environmental node and the adjacent building, which is used to reflect the spatial permeability of the environmental node.

[0027] In some embodiments, reference Figure 2As shown in the figure, this is a schematic flowchart illustrating the process of determining spatial connectivity relationships in some embodiments of this application. The spatial connectivity relationships between all adjacent environmental nodes of the three-dimensional digital twin model constructed through the spatial structural features can be achieved by the following steps: First, in step 1021, the three-dimensional coordinates of each environmental node in the three-dimensional digital twin model are obtained; Then, in step 1022, the diffusion attenuation factor between different adjacent environmental nodes is determined using all three-dimensional coordinates; Finally, in step 1023, the spatial connectivity between all adjacent environmental nodes of the three-dimensional digital twin model is constructed based on all diffusion attenuation factors and the spatial structural features.

[0028] It should be noted that the three-dimensional coordinates mentioned in this application refer to data used to describe the spatial position of each environmental node in the three-dimensional digital twin model, which typically includes coordinate values ​​in three dimensions: X, Y, and Z. The three-dimensional coordinates can be obtained through the data export interface of existing three-dimensional modeling software or LiDAR point cloud data. Preferably, the extraction frequency of the three-dimensional coordinates can be set according to the monitoring and update requirements, such as refreshing the data every 5 to 30 minutes, or it can be extracted in real time according to the model's dynamic update mechanism. This application does not limit this.

[0029] In specific implementation, the diffusion attenuation factor between different adjacent environmental nodes can be determined by using all three-dimensional coordinates in the following manner: First, for each environmental node in the three-dimensional digital twin model, its three-dimensional coordinates in three-dimensional space are extracted, including the X coordinate in the east-west direction, the Y coordinate in the north-south direction, and the Z coordinate in the height direction; then, for each pair of adjacent environmental nodes, the Euclidean distance between their three-dimensional spatial coordinates is calculated; then, according to the exponential attenuation algorithm in the prior art, the Euclidean distance between the two environmental nodes is converted into an attenuation factor. Specifically, the attenuation factor value can be obtained by squaring the Euclidean distance and then performing an exponential function transformation in combination with a preset distance attenuation rate parameter; preferably, the influence intensity of distance on the attenuation factor can be flexibly controlled by setting the attenuation rate parameter to adapt to the accuracy requirements of spatial diffusion simulation in different scenarios; in other embodiments, the inverse distance weighting method, Gaussian kernel function, or thermal diffusion model can also be used to calculate the attenuation factor, and this application does not limit this.

[0030] It should be noted that the diffusion attenuation factor mentioned in this application refers to a numerical parameter used to characterize the degree of attenuation of diffusion between adjacent environmental nodes in a three-dimensional digital twin model with spatial distance. The diffusion attenuation factor can be defined as the value obtained by squaring the three-dimensional spatial Euclidean distance between adjacent environmental nodes and combining it with the distance attenuation rate parameter, and then transforming it through an exponential function. It is used to reflect the nonlinear attenuation characteristics of the diffusion intensity between environmental nodes as a function of distance.

[0031] In specific implementation, the spatial connectivity between all adjacent environmental nodes in the three-dimensional digital twin model, based on all diffusion attenuation factors and the spatial structural features, can be achieved in the following way: First, obtain the diffusion attenuation factors between all adjacent environmental nodes and the corresponding spatial structural features of the nodes, including building volume ratio and spatial occlusion degree; then, for each pair of adjacent environmental nodes, calculate the spatial diffusion value between the two environmental nodes based on their diffusion attenuation factors and the spatial structural features of the two nodes. Specifically, the spatial diffusion value of the pair of adjacent environmental nodes can be obtained by multiplying the diffusion attenuation factor by the smaller building volume ratio and spatial occlusion degree of the two adjacent environmental nodes; next, the matrix composed of the spatial diffusion values ​​between all adjacent environmental nodes in the order of the corresponding environmental node numbers is used as the spatial connectivity between all adjacent environmental nodes in the three-dimensional digital twin model; in other embodiments, other spatial attributes or a weighted fusion algorithm can also be used to construct the spatial diffusion matrix, which is not limited in this application.

[0032] It should be noted that the spatial connectivity relationship mentioned in this application refers to a set of numerical parameters used to characterize the strength of heat or pollution diffusion between different adjacent environmental nodes in a three-dimensional digital twin model. The spatial connectivity relationship can be defined as a spatial diffusion value matrix between adjacent environmental nodes, which is used to reflect the intensity of diffusion between each environmental node under the combined influence of spatial distance attenuation and spatial structural features.

[0033] In step 103, the diffusion intensity index of each environmental node under different thermal diffusion ranges is determined by the dynamic thermal environment data. Then, all diffusion intensity indices are combined with the spatial connectivity relationship to perform spatiotemporal convolution aggregation on the target area to obtain the heat island effect intensity of each environmental node under different thermal diffusion ranges.

[0034] In some embodiments, determining the diffusion intensity index of each environmental node under different thermal diffusion ranges using the dynamic thermal environment data can be achieved through the following steps: Differential analysis was performed on the dynamic thermal environment data to obtain the thermal pulse information of each environmental node; The diffusion intensity index of each environmental node under different thermal diffusion ranges is determined by all thermal pulse information.

[0035] In specific implementation, differential analysis of the thermal environment dynamic data to obtain the thermal pulse information of each environmental node can be achieved in the following way: First, for each environmental node in the three-dimensional digital twin model, its thermal environment dynamic data at continuous time points is obtained; then, differential operation is performed on the thermal environment dynamic data at adjacent time points to calculate the temperature change, and the sequence of temperature change is used as the thermal pulse information of the corresponding environmental node. In other embodiments, other methods can also be used to determine this, which are not limited here.

[0036] It should be noted that the thermal pulse information mentioned in this application refers to a numerical sequence used to characterize the dynamic fluctuation characteristics of the thermal environment of each environmental node in a three-dimensional digital twin model under continuous time changes. The thermal pulse information can be defined as a differential value sequence of the thermal environment dynamic data of each environmental node at adjacent time points, which is used to reflect the amplitude and direction of the temperature change of the environmental node.

[0037] In specific implementation, determining the diffusion intensity index of each environmental node at different thermal diffusion ranges using all thermal pulse information can be achieved in the following way: First, for each environmental node in the three-dimensional digital twin model, the corresponding thermal pulse information is obtained; then, based on the thermal pulse information, frequency domain transformation is performed on each environmental node at different preset scales. Specifically, wavelet transform can be performed on the thermal pulse information to decompose it into multiple frequency components at different scales; next, at the frequency components corresponding to each scale, the sum of squares of the wavelet coefficient vectors of the environmental node at different time points is calculated to obtain the energy value of the corresponding environmental node at that scale; finally, the energy value at different scales is used as the diffusion intensity index of the environmental node at different thermal diffusion ranges. In other embodiments, Fourier transform, Hilbert transform, or other frequency domain analysis methods can be used instead of wavelet transform, and this application does not limit this.

[0038] It should be noted that the diffusion intensity index mentioned in this application refers to the parameter value used to characterize the thermal pulse energy distribution characteristics of each environmental node in the three-dimensional digital twin model under different thermal diffusion ranges. The diffusion intensity index can be defined as the energy value of the sum of squares of wavelet coefficient vectors obtained after frequency domain transformation of thermal pulse information at different frequency domain scales of the environmental node, which is used to reflect the multi-scale intensity characteristics of thermal environment fluctuations of each environmental node.

[0039] It should be noted that there is a correspondence between the scale and the thermal diffusion range because when performing frequency domain transformation on the thermal pulse information, the frequency range covered by different scales corresponds to different temporal variation characteristics of the thermal response of the environmental node. Among them, the smaller scale reflects the information that changes rapidly in a short time, representing the thermal disturbance behavior in a local area, while the larger scale reflects the stable change trend over a longer time range, representing the diffusion process of heat in a larger spatial range. Therefore, the scale can be used to distinguish the thermal response characteristics under different thermal diffusion ranges. Furthermore, the energy value of the wavelet coefficient vector calculated at each scale reflects the change intensity of the thermal pulse signal at the corresponding scale, and can thus be used as a diffusion intensity index of the environmental node within the thermal diffusion range to measure the degree of thermal response generated by the environmental node during thermal diffusion at different scales.

[0040] In some embodiments, the heat island effect intensity of each environmental node in different thermal diffusion ranges can be obtained by performing spatiotemporal convolution aggregation on the target region by combining all diffusion intensity indices with the spatial connectivity relationship, using the following steps: A spatiotemporal thermal diffusion map model of the target region is constructed by combining all diffusion intensity indices and the aforementioned spatial connectivity relationships with a graph convolutional network algorithm. Based on the spatiotemporal heat diffusion map model, each environmental node is convolved and aggregated to obtain the intensity of the heat island effect of each environmental node in different heat diffusion ranges.

[0041] In specific implementation, the spatiotemporal thermal diffusion map model of the target region can be constructed by combining all diffusion intensity indicators and the spatial connectivity relationship with the graph convolutional network algorithm in the following manner: First, for each environmental node in the three-dimensional digital twin model, its diffusion intensity indicator under different thermal diffusion ranges is obtained as the node feature vector of the environmental node at each time step; then, based on the spatial connectivity relationship between all adjacent environmental nodes in the three-dimensional digital twin model, the environmental nodes are respectively regarded as nodes in the graph model, and the spatial diffusion value between each pair of adjacent environmental nodes is regarded as the edge weight between the corresponding nodes in the graph model; next, based on the node feature vector and the edge weight, the input graph data structure of the graph convolutional network is constructed, wherein the node feature matrix is ​​composed of the diffusion intensity indicators of each environmental node arranged in the order of node number, and the edge weight matrix is ​​composed of the spatial connectivity relationship matrix; finally, the node feature matrix and the edge weight matrix are input into the graph convolutional network model as input data for constructing the spatiotemporal thermal diffusion map model of the target region. In other embodiments, graph attention networks or other graph-based deep learning algorithms can also be used to replace the graph convolutional network algorithm, and this application does not limit this.

[0042] It should be noted that the spatiotemporal thermal diffusion graph model described in this application refers to a graph structure model used to characterize the thermal environment fluctuation characteristics and spatial correlation of each environmental node in a three-dimensional digital twin model within a multi-scale thermal diffusion range. The spatiotemporal thermal diffusion graph model is composed of a node feature matrix and an edge weight matrix. The node feature matrix can be defined as a matrix obtained by arranging the diffusion intensity indices of each environmental node under different thermal diffusion ranges, and is used to describe the temporal thermal characteristics of the environmental nodes. The edge weight matrix can be defined as a matrix composed of the spatial diffusion values ​​between each adjacent environmental node, and is used to describe the spatial coupling relationship between the environmental nodes.

[0043] In specific implementation, the heat island effect intensity of each environmental node in different heat diffusion ranges can be obtained by convolutional aggregation of each environmental node according to the spatiotemporal heat diffusion graph model, which can be achieved in the following way: First, the node feature matrix of each environmental node in the spatiotemporal heat diffusion graph model is input into the graph convolutional network, wherein the node feature matrix includes the diffusion intensity index of the environmental node in different heat diffusion ranges; then, for each environmental node, the neighborhood feature aggregation operation is performed on each environmental node using the convolution operator in the graph convolutional network. Specifically, the feature vector of the environmental node is weighted and superimposed by taking the environmental node as the center, combining the node feature vector of its neighboring environmental nodes and the corresponding edge weights in the spatial connectivity relationship, and the weighted result is nonlinearly transformed by the activation function to obtain the updated feature vector of the environmental node; then, the feature components in different heat diffusion ranges in the final feature vector of each environmental node obtained after convolutional aggregation are taken as the heat island effect intensity of the corresponding environmental node in different heat diffusion ranges. In other embodiments, other methods can also be used to achieve this, which are not limited here.

[0044] It should be noted that the heat island effect intensity mentioned in this application refers to the numerical value obtained by aggregating the diffusion intensity index of each environmental node within different thermal diffusion ranges based on the spatiotemporal heat diffusion map model and through graph convolutional network to perform neighborhood feature aggregation calculation. This value is used to characterize the thermal environment fluctuation intensity of the environmental node at the corresponding thermal diffusion scale and reflects the thermal environment intensity characteristics of the comprehensive influence of local and neighborhood thermal diffusion of the environmental node.

[0045] In step 104, pollution diffusion fields of each environmental node in a preset spatial neighborhood are generated based on pollution monitoring data of different environmental nodes. Then, the impact of the heat island effect intensity on the pollution diffusion field is evaluated to obtain the thermal impact pollution diffusion risk of each environmental node in different thermal diffusion ranges.

[0046] In some embodiments, generating the pollution diffusion field of each environmental node in a preset spatial neighborhood based on pollution monitoring data from different environmental nodes can be achieved through the following steps: Obtain pollution monitoring data for each environmental node in the three-dimensional digital twin model; Select an environment node as the selected environment node; The amount of pollution drift of the selected environmental node in the preset spatial neighborhood is determined by using pollution monitoring data of the selected environmental node. Construct a pollution diffusion field for the selected environmental node in a preset spatial neighborhood based on all pollution drift amounts; Continue to determine the pollution diffusion field of the remaining environmental nodes in the preset spatial neighborhood.

[0047] It should be noted that the pollution monitoring data mentioned in this application refers to a set of observational data used to characterize the concentration and change characteristics of pollutants at the location of each environmental node in the three-dimensional digital twin model. The pollution monitoring data includes, but is not limited to, the concentration values ​​of air pollutants (e.g., nitrogen dioxide), the concentration values ​​of water pollutants, and environmental meteorological data (e.g., wind speed, wind direction, and temperature) at different time points of the environmental nodes. The collection frequency of the pollution monitoring data can be selected according to the settings. In other embodiments, the pollution monitoring data of each environmental node in the three-dimensional digital twin model can also be obtained by means of IoT sensor networks, remote sensing satellite observation, UAV inspection and sampling, ground monitoring station deployment, third-party environmental monitoring services, or pollution source emission reports. This application does not limit this.

[0048] In specific implementation, determining the multiple pollution drift amounts of a selected environmental node in a preset spatial neighborhood using pollution monitoring data of the selected environmental node can be achieved in the following way: First, the size of the preset spatial neighborhood is determined; then, the pollution monitoring data of the selected environmental node is obtained; subsequently, the pollution concentration data of the selected environmental node and other environmental nodes within the preset spatial neighborhood at the same time point are obtained, and the pollution concentration difference between the selected environmental node and each neighboring node is determined as the corresponding pollution drift amount, thereby obtaining the multiple pollution drift amounts of the selected environmental node in the preset spatial neighborhood. The size of the spatial neighborhood can be set according to actual application needs and environmental characteristics. Preferably, it can be set within a radius of 50 meters to 500 meters. The specific value can be determined in combination with the pollutant diffusion characteristics and monitoring accuracy requirements. In other embodiments, it can also be flexibly adjusted according to the diffusion distance or regional characteristics of different pollutants. This application does not limit this.

[0049] It should be noted that the pollution drift amount mentioned in this application refers to the difference in pollution concentration between a selected environmental node and its neighboring environmental nodes within a preset spatial neighborhood at the same point in time. This is used to characterize the concentration change range and migration trend of pollutants within the spatial neighborhood, and to reflect the spatial diffusion characteristics of pollutants between environmental nodes.

[0050] In specific implementation, constructing the pollution diffusion field of the selected environmental node in the preset spatial neighborhood based on all pollution drift amounts can be achieved in the following way: First, for the selected environmental node, within the preset spatial neighborhood, the pollution drift amounts between the selected environmental node and each neighboring node are obtained respectively; then, based on the magnitude of each pollution drift amount and the spatial position coordinates of the corresponding neighboring node relative to the selected environmental node, all pollution drift amounts are mapped to a three-dimensional spatial coordinate system; specifically, a weighting factor of pollution concentration difference and spatial distance can be used to allocate each pollution drift amount to the corresponding spatial position to obtain the pollution concentration distribution of the selected environmental node in the preset spatial neighborhood; furthermore, by interpolating the pollution drift amounts at all mapped positions, a continuous pollution diffusion field is generated. Preferably, an inverse distance weighted interpolation method or a Gaussian kernel function can be used for interpolation processing to smooth the pollution concentration distribution and obtain the pollution diffusion field of the selected environmental node in the preset spatial neighborhood; other methods can also be used in other embodiments, and this application does not limit them.

[0051] It should be noted that the pollution diffusion field mentioned in this application refers to a continuous pollution concentration distribution field constructed by spatial interpolation method based on the amount of pollution drift and its spatial location between a selected environmental node and each neighboring node in its preset spatial neighborhood. This field is used to characterize the spatial diffusion characteristics and concentration gradient changes of pollutants within the neighborhood and to reflect the migration trend of pollutants in the environmental space.

[0052] In some embodiments, assessing the impact of the heat island effect intensity on the pollution diffusion field and obtaining the thermal impact pollution diffusion risk of each environmental node in different thermal diffusion ranges can be achieved through the following steps: Select an environment node as the selected environment node; Evaluate the multiple diffusion influence components between the intensity of the heat island effect and the corresponding pollution diffusion field in different thermal diffusion ranges of selected environmental nodes; Determine the thermal impact pollution diffusion risk of selected environmental nodes within different thermal diffusion ranges based on all diffusion impact components; Continue to determine the risk of thermal impact pollution diffusion at remaining environmental nodes within different thermal diffusion ranges.

[0053] In specific implementation, evaluating the multiple diffusion influence components between the heat island effect intensity and the corresponding pollution diffusion field in different thermal diffusion ranges of a selected environmental node can be achieved in the following way: First, obtain the heat island effect intensity of the selected environmental node in different thermal diffusion ranges, and the pollution diffusion field of the selected environmental node in a preset spatial neighborhood; then, for each thermal diffusion range, multiply the heat island effect intensity by the pollution drift amount of each adjacent environmental node in the pollution diffusion field to obtain the diffusion influence component of the selected environmental node corresponding to each adjacent environmental node in that thermal diffusion range; next, perform a weighted summation of the diffusion influence component values ​​corresponding to all adjacent environmental nodes in the same thermal diffusion range. Preferably, the reciprocal of the spatial distance between the adjacent environmental node and the selected environmental node can be used as the weighting coefficient of the diffusion influence component corresponding to that node to obtain the diffusion influence component of the selected environmental node in that thermal diffusion range, thereby determining the different thermal diffusion ranges of the selected environmental node. The heat island effect intensity within the diffusion range and the corresponding pollution diffusion field have multiple diffusion influence components. As a preferred embodiment, determining the thermal impact pollution diffusion risk of a selected environmental node in different thermal diffusion ranges based on all diffusion influence components can be achieved in the following manner: First, obtain all diffusion influence components of the selected environmental node under different thermal diffusion ranges; then, normalize the diffusion influence components under each thermal diffusion range so that the values ​​of all diffusion influence components under all thermal diffusion ranges are within the same numerical range, thereby eliminating the influence of different dimensions or value ranges; next, use each normalized diffusion influence component as the thermal impact pollution diffusion risk of the selected environmental node under the corresponding thermal diffusion range, thus obtaining the thermal impact pollution diffusion risk of the selected environmental node in different thermal diffusion ranges. In other embodiments, percentile methods, standardization, or other normalization methods can also be used to process the diffusion influence components; this application does not limit this.

[0054] It should be noted that the diffusion impact component described in this application is used to quantify the degree of mutual influence between the thermal environment and the diffusion of pollutants; in addition, the thermal impact pollution diffusion risk refers to the value obtained by normalizing the diffusion impact component of the selected environmental node in different thermal diffusion ranges, which is used to reflect the risk level of thermal pollution superposition and propagation at each thermal diffusion scale.

[0055] In step 105, a multi-scale thermal pollution report for the target area is generated by combining all thermal impact pollution diffusion risks with preset monitoring thresholds.

[0056] In some embodiments, generating a multi-scale thermal pollution report for a target area by combining all thermal impact pollution diffusion risks with preset monitoring thresholds can be achieved through the following steps: Set monitoring thresholds for different thermal diffusion ranges; The thermal pollution risk level of each environmental node in different thermal diffusion ranges was determined by all monitoring thresholds and all thermal impact pollution diffusion risks. A multi-scale thermal pollution report for the target area is generated based on all thermal pollution risk levels.

[0057] It should be noted that the monitoring threshold mentioned in this application refers to the threshold used to determine whether the risk of thermal pollution diffusion at each environmental node is within an acceptable range under different thermal diffusion ranges. Preferably, the monitoring threshold can be determined based on the environmental sensitivity level, pollutant type, regional population density, and environmental protection policy standards of the target area. For example, for general industrial areas, the monitoring threshold can be set higher, indicating that a certain degree of thermal pollution superposition effect is allowed under the thermal diffusion range. For environmentally sensitive areas (such as residential areas or ecological protection areas), the monitoring threshold can be set lower to ensure that the risk of thermal pollution diffusion remains at a low level under high environmental protection requirements. In other embodiments, the monitoring threshold can also be determined based on historical environmental monitoring data, national or local pollution control standards, or through expert evaluation methods. This application does not limit this.

[0058] For specific implementation, refer to Figure 3As shown in the figure, this is a schematic diagram illustrating the structure for determining the thermal pollution risk level in some embodiments of this application. The determination of the thermal pollution risk level of each environmental node in different thermal diffusion ranges, based on all monitoring thresholds and all thermal impact pollution diffusion risks, can be achieved in the following manner: First, for each environmental node in the three-dimensional digital twin model, its thermal impact pollution diffusion risk under different thermal diffusion ranges is obtained; then, the thermal impact pollution diffusion risk is compared with the monitoring thresholds. If the thermal impact pollution diffusion risk is greater than or equal to the monitoring threshold under the corresponding thermal diffusion range, the environmental node is determined to be at a high risk level under the corresponding thermal diffusion range; if the thermal impact pollution diffusion risk is less than the monitoring threshold under the corresponding thermal diffusion range, the environmental node is determined to be at a low risk level under the corresponding thermal diffusion range. Preferably, it can be further divided into multiple risk levels. For example, based on different multiples of the monitoring thresholds, the thermal pollution risk level can be divided into high risk, medium risk, and low risk to achieve a more refined thermal pollution risk assessment. In other implementations, fuzzy logic, probabilistic statistics, or machine learning algorithms can also be used to determine the thermal pollution risk level, and this application does not limit this. As a preferred embodiment, generating a multi-scale thermal pollution report for the target area based on all thermal pollution risk levels can be achieved in the following way: First, obtain the thermal pollution risk level of each environmental node in the three-dimensional digital twin model under different thermal diffusion ranges; then, perform statistical and visualization processing on the spatial distribution of the thermal pollution risk levels of each environmental node to generate a thermal pollution risk distribution map of the target area under each thermal diffusion range; next, mark the high-risk, medium-risk, and low-risk areas under each thermal diffusion range, and count the number and proportion of environmental nodes with different risk levels; finally, summarize the thermal pollution risk distribution map, statistical data, and analysis conclusions to generate a multi-scale thermal pollution report for the target area. In other implementations, the multi-scale thermal pollution report can also be generated by combining three-dimensional visualization technology, geographic information systems, or intelligent analysis platforms, and this application does not limit this.

[0059] In another aspect, in some embodiments, this application provides an ecological environment monitoring system, with reference to... Figure 4 The figure is a schematic diagram of the structure of an ecological environment monitoring system according to some embodiments of this application. The ecological environment monitoring system 200 includes: a construction module 201, a processing module 202, and an execution module 203, which are described below: Construction module 201, in this application, is mainly used to construct a three-dimensional digital twin model of a specified city in a target area, wherein the three-dimensional digital twin model includes dynamic thermal environment data of different environmental nodes; Processing module 202, in this application, is mainly used to determine the spatial structural features of different environmental nodes in the three-dimensional digital twin model, and then construct the spatial connectivity relationship between all adjacent environmental nodes of the three-dimensional digital twin model through the spatial structural features; In addition, the processing module 202 in this application is also used to determine the diffusion intensity index of each environmental node under different thermal diffusion ranges through the thermal environment dynamic data, and then combine all diffusion intensity indices with the spatial connectivity relationship to perform spatiotemporal convolution aggregation on the target area to obtain the heat island effect intensity of each environmental node under different thermal diffusion ranges. In addition, the processing module 202 in this application is also used to generate a pollution diffusion field of each environmental node in a preset spatial neighborhood based on the pollution monitoring data of different environmental nodes, and then assess its impact on the pollution diffusion field based on the intensity of the heat island effect to obtain the thermal impact pollution diffusion risk of each environmental node in different heat diffusion ranges. The execution module 203 in this application is mainly used to generate a multi-scale thermal pollution report for the target area by combining all thermal impact pollution diffusion risks with preset monitoring thresholds.

[0060] In addition, this application also provides a computer device, which includes a memory and a processor. The memory stores code, and the processor is configured to acquire the code and execute the above-described ecological environment monitoring method.

[0061] In some embodiments, reference Figure 5 This figure is an internal structural diagram of a computer device for implementing an ecological environment monitoring method according to some embodiments of this application. The ecological environment monitoring method in the above embodiments can be implemented through... Figure 5 The computer device shown is used to implement this, and the computer device 300 includes at least one processor 301, a communication bus 302, a memory 303, and at least one communication interface 304.

[0062] The processor 301 may be a general-purpose central processing unit (CPU), an application-specific integrated circuit (ASIC), or one or more devices used to control the execution of the ecological environment monitoring method in this application.

[0063] The communication bus 302 is used to transmit information between the aforementioned components.

[0064] Memory 303 may be a read-only memory (ROM) or other type of static storage device capable of storing static information and instructions, random access memory (RAM) or other type of dynamic storage device capable of storing information and instructions, or electrically erasable programmable read-only memory (EEPROM), compact disc read-only memory (CDROM) or other optical disc storage, optical disc storage (including compressed optical discs, laser discs, optical discs, digital versatile optical discs, Blu-ray discs, etc.), magnetic disks or other magnetic storage devices, or any other medium capable of carrying or storing desired program code in the form of instructions or data structures and accessible by a computer, but not limited thereto. Memory 303 may exist independently and be connected to processor 301 via communication bus 302. Memory 303 may also be integrated with processor 301.

[0065] The memory 303 stores program code for executing the scheme of this application, and its execution is controlled by the processor 301. The processor 301 executes the program code stored in the memory 303. The program code may include one or more software modules. In the above embodiments, the ecological environment monitoring method can be implemented by the processor 301 and one or more software modules in the program code in the memory 303.

[0066] Communication interface 304 uses any transceiver-like device to communicate with other devices or communication networks, such as Ethernet, radio access network (RAN), wireless local area networks (WLAN), etc.

[0067] In a specific implementation, as one example, a computer device may include multiple processors, each of which may be a single-core processor or a multi-core processor. Here, a processor may refer to one or more devices, circuits, and / or processing cores for processing data (e.g., computer program instructions).

[0068] The aforementioned computer device can be a general-purpose computer device or a special-purpose computer device. In specific implementations, the computer device may be a desktop computer, a portable computer, a network server, a handheld digital assistant (PDA), a mobile phone, a tablet computer, a wireless terminal device, a communication device, or an embedded device. This application does not limit the type of computer device.

[0069] In addition, this application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described ecological environment monitoring method.

[0070] In summary, the ecological environment monitoring system and method disclosed in this application involves constructing a three-dimensional digital twin model of a designated city in a target area, wherein the three-dimensional digital twin model includes dynamic thermal environment data of different environmental nodes; determining the spatial structural characteristics of different environmental nodes in the three-dimensional digital twin model, and then constructing spatial connectivity relationships between all adjacent environmental nodes in the three-dimensional digital twin model based on the spatial structural characteristics; determining the diffusion intensity index of each environmental node under different thermal diffusion ranges based on the dynamic thermal environment data, and then performing spatiotemporal convolution aggregation of all diffusion intensity indices with the spatial connectivity relationships to obtain the heat island effect intensity of each environmental node in different thermal diffusion ranges; generating a pollution diffusion field of each environmental node in a preset spatial neighborhood based on pollution monitoring data of different environmental nodes, and then assessing its impact on the pollution diffusion field based on the heat island effect intensity to obtain the thermal impact pollution diffusion risk of each environmental node in different thermal diffusion ranges; generating a multi-scale thermal pollution report of the target area by combining all thermal impact pollution diffusion risks with preset monitoring thresholds; and enabling multi-scale monitoring of urban thermal pollution based on the spatiotemporal coordination mechanism of digital twins.

[0071] Although preferred embodiments of this application have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments as well as all changes and modifications falling within the scope of this application.

[0072] Obviously, those skilled in the art can make various modifications and variations to this application without departing from the spirit and scope of this application. Therefore, if such modifications and variations fall within the scope of the claims of this application and their equivalents, this application also intends to include such modifications and variations.

Claims

1. An ecological environment monitoring method, characterized in that, Includes the following steps: Construct a three-dimensional digital twin model of a specified city in a target area, wherein the three-dimensional digital twin model includes dynamic thermal environment data of different environmental nodes; The spatial structural features of different environmental nodes in the three-dimensional digital twin model are determined, and then the spatial connectivity between all adjacent environmental nodes in the three-dimensional digital twin model is constructed through the spatial structural features. The diffusion intensity index of each environmental node under different thermal diffusion ranges is determined by the dynamic data of the thermal environment. Then, all diffusion intensity indices are combined with the spatial connectivity relationship to perform spatiotemporal convolution aggregation on the target area to obtain the heat island effect intensity of each environmental node under different thermal diffusion ranges. Based on pollution monitoring data of different environmental nodes, a pollution diffusion field of each environmental node in a preset spatial neighborhood is generated. Then, based on the intensity of the heat island effect, its impact on the pollution diffusion field is assessed, and the thermal impact pollution diffusion risk of each environmental node in different heat diffusion ranges is obtained. A multi-scale thermal pollution report for the target area is generated by combining all thermal impact pollution spread risks with preset monitoring thresholds.

2. The method as described in claim 1, characterized in that, Determining the spatial structural features of different environmental nodes in the three-dimensional digital twin model specifically includes: Obtain the spatial parameters of each environmental node in the three-dimensional digital twin model; The spatial structural features of different environmental nodes in the three-dimensional digital twin model are determined by the spatial parameters.

3. The method as described in claim 1, characterized in that, The spatial connectivity relationships between all adjacent environmental nodes in the three-dimensional digital twin model constructed using the aforementioned spatial structural features specifically include: Obtain the three-dimensional coordinates of each environmental node in the three-dimensional digital twin model; The diffusion attenuation factor between different adjacent environmental nodes is determined using all three-dimensional coordinates. Based on all diffusion attenuation factors and the spatial structural features, the spatial connectivity relationships between all adjacent environmental nodes in the three-dimensional digital twin model are constructed.

4. The method as described in claim 1, characterized in that, Specifically, determining the diffusion intensity index of each environmental node under different thermal diffusion ranges using the aforementioned dynamic thermal environment data includes: Differential analysis was performed on the dynamic thermal environment data to obtain the thermal pulse information of each environmental node; The diffusion intensity index of each environmental node under different thermal diffusion ranges is determined by all thermal pulse information.

5. The method as described in claim 1, characterized in that, By combining all diffusion intensity indicators with the aforementioned spatial connectivity, spatiotemporal convolution aggregation is performed on the target region to obtain the heat island effect intensity of each environmental node in different thermal diffusion ranges, specifically including: A spatiotemporal thermal diffusion map model of the target region is constructed by combining all diffusion intensity indices and the aforementioned spatial connectivity relationships with a graph convolutional network algorithm. Based on the spatiotemporal heat diffusion map model, each environmental node is convolved and aggregated to obtain the intensity of the heat island effect of each environmental node in different heat diffusion ranges.

6. The method as described in claim 1, characterized in that, The generation of pollution diffusion fields for each environmental node in a preset spatial neighborhood, based on pollution monitoring data from different environmental nodes, specifically includes: Obtain pollution monitoring data for each environmental node in the three-dimensional digital twin model; Select an environment node as the selected environment node; The amount of pollution drift of the selected environmental node in the preset spatial neighborhood is determined by using pollution monitoring data of the selected environmental node. Construct a pollution diffusion field for the selected environmental node in a preset spatial neighborhood based on all pollution drift amounts; Continue to determine the pollution diffusion field of the remaining environmental nodes in the preset spatial neighborhood.

7. The method as described in claim 1, characterized in that, Based on the assessment of the intensity of the heat island effect on the pollution diffusion field, the specific thermal impact pollution diffusion risks of each environmental node in different thermal diffusion ranges include: Select an environment node as the selected environment node; Evaluate the multiple diffusion influence components between the intensity of the heat island effect and the corresponding pollution diffusion field in different thermal diffusion ranges of selected environmental nodes; Determine the thermal impact pollution diffusion risk of selected environmental nodes within different thermal diffusion ranges based on all diffusion impact components; Continue to determine the risk of thermal impact pollution diffusion at remaining environmental nodes within different thermal diffusion ranges.

8. The method as described in claim 1, characterized in that, A multi-scale thermal pollution report for the target area is generated by combining all thermal impact pollution diffusion risks with preset monitoring thresholds, specifically including: Set monitoring thresholds for different thermal diffusion ranges; The thermal pollution risk level of each environmental node in different thermal diffusion ranges was determined by all monitoring thresholds and all thermal impact pollution diffusion risks. A multi-scale thermal pollution report for the target area is generated based on all thermal pollution risk levels.

9. The method as described in claim 1, characterized in that, The environmental node refers to a spatial unit within the target area that is divided according to a preset spatial gridding rule.

10. An ecological environment monitoring system, characterized in that, include: A construction module is used to construct a three-dimensional digital twin model of a specified city in a target area, wherein the three-dimensional digital twin model includes dynamic thermal environment data of different environmental nodes; The processing module is used to determine the spatial structural features of different environmental nodes in the three-dimensional digital twin model, and then construct the spatial connectivity relationship between all adjacent environmental nodes of the three-dimensional digital twin model through the spatial structural features. The processing module is also used to determine the diffusion intensity index of each environmental node under different thermal diffusion ranges through the thermal environment dynamic data, and then combine all diffusion intensity indices with the spatial connectivity relationship to perform spatiotemporal convolution aggregation on the target area to obtain the heat island effect intensity of each environmental node under different thermal diffusion ranges. The processing module is also used to generate pollution diffusion fields of each environmental node in a preset spatial neighborhood based on pollution monitoring data of different environmental nodes, and then assess its impact on the pollution diffusion field based on the intensity of the heat island effect to obtain the thermal impact pollution diffusion risk of each environmental node in different heat diffusion ranges. The execution module is used to generate a multi-scale thermal pollution report for the target area by combining all thermal impact pollution spread risks with preset monitoring thresholds.

Images